Agent Lightning

이 문서는 프롬프트 자동 최적화 프레임워크인 Agent lightning을 어떻게 사용하는지 설명합니다.

Agent Lightning is the absolute trainer to light up AI agents.

• Embraces Algorithms like Reinforcement Learning, Automatic Prompt Optimization, Supervised Fine-tuning and more. 🤗

How to Read this Documentation

This documentation is organized into the following parts:

• 전반적인 agentlightning 원리와 사용방법, 개념: [Write First Algorithm](how-to/write-first-algorithm.md)

How-to Recipes (e.g., [Train SQL Agent with RL](how-to/train-sql-agent.md)) - Practical examples of training agents and customizing algorithms.

• Learning More (e.g., [Debugging](tutorials/debug.md)) - Guides on specific topics like debugging or parallelization.
• Algorithm Zoo (e.g., [APO](algorithm-zoo/apo.md)) - References for built-in algorithms.
• Deep Dive (e.g., [Bird's Eye View](deep-dive/birds-eye-view.md)) - For a deeper understanding of what Agent-lightning is doing under the hood.